Abstract
A new texture defect detection method for automatic visual inspection systems is presented in this paper. It divides an analysed texture image into non-overlapping samples, and then calculates features of each sample using the Principle Component Analysis technique. Finally, the fuzzy c-means clustering of these features is applied to classify the sample as defective or non-defective. Unlike many existing methods, the proposed scheme does not require a training step to collect defective and non-defective texture samples. The experimental results show that the method is at least as effective and accurate as many existing methods for image texture defect detection.
Similar content being viewed by others
References
Conners R.W., McMillin C.W., Lin K., Vasquez-Espinosa R.E.: Identifying and locating surface defects in wood: part of an automated lumber processing system. IEEE Trans. PAMI 5(6), 573–583 (1983)
Dewaele, P.; van Gool, P.; Oosterlinck, A.: Texture inspection with self-adaptive convolution filters. In: 9th International Conference on Pattern Recognition, Italy, pp. 56–60 (1988)
Jain, A.K.; Farrokhnia, F.; Alman, D.H.: Texture analysis of automotive finishes. In: Machine Vision Applications Conference, USA, pp. 1–16 (1990)
Amet, A.L.; Ertüzün, A.; Erçil, A.: Texture defect detection using subband domain co–occurrence matrices. In: Proceedings of IEEE Southeast Symposium on Image Analysis and Interpretation, Turkey, pp. 205–210 (1998)
Siegel, M.; Gunatilake, P.: Enhanced remote visual inspection of aircraft skin, Proceedings of the Intelligent NDE Sciences for Aging and Futuristic Aircraft Workshop, USA, pp. 101–112 (1997)
Bolter, R.; Fernandez, G.; Lenz, G.: Detection of flaws on melamine faced chipboards using wavelet based texture analysis. In: 25th Workshop of the Austrian Association for Pattern Recognition, Austria, pp. 59–165 (2001)
Schael, M.: Texture defect detection using invariant textural features. In: DAGM Symposium, Germany, pp. 17–24 (2001)
Maaenpaa T., Turtinen M., Pietikainen M.: Real-time surface inspection by texture. Real Time Imaging 9(6), 289–296 (2003)
Morrison D.F.: Multivariate Statistical Methods. McGraw-Hill Book Company, New York (1976)
Höppner F., Klawonn R., Kruse T.: Fuzzy Cluster Analysis. Wiley, Chichester (1999)
http://www.imageafter.com. The data-base Image After.
Partio, M.; Cramariuc, B.; Gabbouj, M.; Visa, A.: Rock texture retrieval using grey level co-occurance matrix. In: 5th Nordic Signal Processing Symposium, Norway (2002)
Wiltschi K., Pinz A., Lindeberg T.: An automatic assessment scheme for steel quality inspection. Mach. Vis. Appl. 12, 113–128 (2000)
Elbehiery, H.; Hefnawy, A.; Elewa, M.: Visual inspection for fired ceramic tile’s surface defects using wavelet analysis. In: 1st International Computer Engineering Conference New Technologies for the Information Society, Egypt (2004)
Stojanovic R., Mitropulos P., Koulamas C., Karayiannis Y., Koubias S., Papadopoulos G.: Real-time vision-based system for textile fabric inspection. Real-Time Imaging 7(6), 507–518 (2001)
Fujiwara, H.; Zhang, Z.; Toda, H.: Textile surface inspection by using translation invariant wavelet transform. In: IEEE International Symposium on Computational Intelligence in Robotics and Automation, Japan, pp. 1427–1432 (2003)
Medina R., Gayubo F., González-Rodrigo L.M., Olmedo D., Gómez-García-Bermejo J., Zalama E., Perán J.R.: Fault-image detection algorithm based on visual perception. Int. J. Adv. Manuf. Technol. 57(9–12), 1087–1097 (2011)
Mak K.L., Peng P., Yiu K.F.C.: Fabric defect detection using morphological filters. Image Vis. Comput. 27, 1585–1592 (2009)
Rosati G., Boschetti G., Biondi A., Rossi A.: Real-time defect detection on highly reflective curved surfaces. Optics Lasers Eng. 47(3–4), 379–384 (2009)
Majid Z.A., Mohsin R.: Failure investigation of natural gas pipeline. Arabian J. Sci. Eng. 37, 1083–1088 (2012)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mosorov, V., Tomczak, L. Image Texture Defect Detection Method Using Fuzzy C-Means Clustering for Visual Inspection Systems. Arab J Sci Eng 39, 3013–3022 (2014). https://doi.org/10.1007/s13369-013-0920-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13369-013-0920-7